Scanning all new published packages on PyPI I know that the quality is often quite bad. I try to filter out the worst ones and list here the ones which might be worth a look, being followed or inspire you in some way.

tempeh
Machine Learning Performance Testing Framework

torch3d
Datasets and network architectures for 3D deep learning in PyTorch

trains-agent
Trains-Agent DevOps for deep learning (DevOps for TRAINS)

tree-lstm
pytorch tree lstm package. This repository contains a Pytorch Implementation of ‘Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks ‘ (https://…/1503.00075 ). This contains two type of tree-lstm (Child sum, N-ary). This was tested by Python 3.6, Pytorch 1.3.0., and this internally uses dgl 0.4.0 This repository referenced https://…/tree_lstm.py

trelawney
Generic Interpretability package. Trelawney is a general interpretability package that aims at providing a common api to use most of the modern interpretability methods to shed light on sklearn compatible models (support for Keras and XGBoost are tested).

arus
Activity Recognition with Ubiquitous Sensing

cma-es
Covariance Matrix Adaptation Evolution Strategy (CMA-ES) implemented with TensorFlow v2. The CMA-ES (Covariance Matrix Adaptation Evolution Strategy) is an evolutionary algorithm for difficult non-linear non-convex black-box optimisation problems in continuous domain. It is considered as state-of-the-art in evolutionary computation and has been adopted as one of the standard tools for continuous optimisation in many (probably hundreds of) research labs and industrial environments around the world.

mozilla-fldp
Federated Learning Experimentation

musco-pytorch
MUSCO: Multi-Stage COmpression of Neural Networks

waymo-od-tf2-0
Waymo Open Dataset libraries.

Advertisements